{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/characterbert","slug":"characterbert","name":"CharacterBERT","full_name":"CharacterBERT","full_name_withheld":false,"description_markdown":"CharacterBERT is a variant of [BERT](https://paperswithcode.com/method/bert) that **drops the wordpiece system** and **replaces it with a CharacterCNN module** just like the one [ELMo](https://paperswithcode.com/method/elmo) uses to produce its first layer representation. This allows CharacterBERT to represent any input token without splitting it into wordpieces. Moreover, this frees BERT from the burden of a domain-specific wordpiece vocabulary which may not be suited to your domain of interest (e.g. medical domain). Finally, it allows the model to be more robust to noisy inputs.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2010.10392v3","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/helboukkouri/character-bert#using-characterbert-in-practice","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":8,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/continuous-prompt-tuning-based-textual","slug":"continuous-prompt-tuning-based-textual","title":"Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing","date":"2022-11-04","arxiv_id":"2211.02483","n_code_links":1,"syntology":null},{"paper":"/paper/characterbert-and-self-teaching-for-improving","slug":"characterbert-and-self-teaching-for-improving","title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos","date":"2022-04-01","arxiv_id":"2204.00716","n_code_links":1,"syntology":null},{"paper":"/paper/signal-in-noise-exploring-meaning-encoded-in","slug":"signal-in-noise-exploring-meaning-encoded-in","title":"Signal in Noise: Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models","date":"2022-03-15","arxiv_id":"2203.07911","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-meaning-encoded-in-random-character","title":"Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/imposing-relation-structure-in-language-model","slug":"imposing-relation-structure-in-language-model","title":"Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning","date":"2021-09-02","arxiv_id":"2109.00840","n_code_links":1,"syntology":null},{"paper":"/paper/uniparma-semeval-2021-task-5-toxic-spans","slug":"uniparma-semeval-2021-task-5-toxic-spans","title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model","date":"2021-03-17","arxiv_id":"2103.09645","n_code_links":1,"syntology":null},{"paper":"/paper/characterbert-reconciling-elmo-and-bert-for","slug":"characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","arxiv_id":"2010.10392","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":3,"n_instrument":3,"unverified":2,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["helboukkouri/character-bert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/aggressive-language-identification-using-word","slug":"aggressive-language-identification-using-word","title":"Aggressive Language Identification Using Word Embeddings and Sentiment Features","date":"2018-08-01","arxiv_id":null,"n_code_links":1,"syntology":null}],"papers_shown":8,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":8,"with_a_code_link":7,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/characterbert/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/characterbert/papers/ran/1","json":"/method/characterbert/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":2},{"task":"/task/relation-extraction","name":"Relation Extraction","papers":2},{"task":"/task/aggression-identification","name":"Aggression Identification","papers":1},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/clinical-concept-extraction","name":"Clinical Concept Extraction","papers":1},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1},{"task":"/task/drug-drug-interaction-extraction","name":"Drug–drug Interaction Extraction","papers":1},{"task":"/task/entity-typing","name":"Entity Typing","papers":1},{"task":"/task/language-identification","name":"Language Identification","papers":1},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":1},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":1},{"task":"/task/passage-retrieval","name":"Passage Retrieval","papers":1},{"task":null,"name":"Relation","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/semantic-similarity","name":"Semantic Similarity","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1},{"task":"/task/sentence-embeddings","name":"Sentence Embeddings","papers":1},{"task":"/task/toxic-spans-detection","name":"Toxic Spans Detection","papers":1}],"tasks_shown":20,"n_tasks":22,"usage_by_year":[{"year":"2018","papers":1},{"year":"2020","papers":1},{"year":"2021","papers":3},{"year":"2022","papers":3}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/characterbert"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=CharacterBERT","read_at":"2026-10-05T00:53:34+00:00","query":"CharacterBERT","kind":"paper","have":"unverified_code","tier":"harvested","verified_implementation":false,"level":1,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2010.10392"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":null,"repositories":{"listed":2,"in_graph":2,"list_truncated":false,"strongest_link":"official"},"retrieve_with":"get_harvested_code_for_paper(arxiv_id='2010.10392')","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2010.10392","citations":178},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'CharacterBERT'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2010.10392","page":"/paper/characterbert-reconciling-elmo-and-bert-for","syntology_url":"https://syntology.ai/paper/2010.10392","in_graph_layer":true,"samples":8,"ran":6,"n_ran_checked":3,"n_instrument":3,"unverified":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"harvested code stored, below machine verification (unverified_code; harvested), served level V1. Repositories: 2 listed of 2 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2010.10392, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2010.10392) is about this method is not checked.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"b2e8b0b787f66a6d833dfd895c96b684b59a176efacb42ef09875f4e90cc6749","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}